← All Test Cases

FB-001

v040 F feedback

critical

Repetitions

Documents

Questions

Reasoning

DETERMINISTIC

v040 F1 feedback wrong

📖 In Plain English

No description available yet for category "v040_F_feedback".

⚙️ How a single rep runs

① Generate

Model creates 0 synthetic documents and 0 questions with unique canary tokens

→ Fresh content per run prevents memorization and proves real retrieval

② Ingest (MCP)

Model calls brain_ingest to store the 0 documents

→ Tests the brain's storage and indexing pipeline

③ Query (MCP)

Model answers the question using brain retrieval tools (search, fetch, context_pack, etc.)

→ Core test — does the brain return correct evidence and let the model build a faithful answer?

④ Evaluate

Model judges the answer against ground truth (the document it generated in phase 1)

→ Produces a score 0–100 with detailed sub-scores (retrieval, fidelity, reasoning, etc.)

This rep is run 1 times per test run. A pass requires score ≥ 85 and no critical failures.

🔬 Technical Instructions (raw prompts sent to AI)

Recent Run History

0 runs

No runs have included this test yet.

📄 Raw YAML cases/v040_F_feedback/FB-001.yaml

schema_version: "1.0"
test_id: "FB-001"
category: "v040_F_feedback"
kind: "deterministic"
severity: "critical"
repetitions: 1
reasoning_type: "DETERMINISTIC"
num_documents: 0
num_questions: 0
tags: ["v040", "F1", "feedback", "wrong"]
assertion_module: "v040.F_feedback.fb_001"
description: |
  Feedback 'wrong' halves importance (floor 0.05) and increments Person.wrong_claim_count on every linked source.